Please use this identifier to cite or link to this item: http://localhost/handle/Hannan/185675
Title: Top-Down Visual Saliency via Joint CRF and Dictionary Learning
Authors: Jimei Yang;Ming-Hsuan Yang
Year: 2017
Publisher: IEEE
Abstract: Top-down visual saliency is an important module of visual attention. In this work, we propose a novel top-down saliency model that jointly learns a Conditional Random Field (CRF) and a visual dictionary. The proposed model incorporates a layered structure from top to bottom: CRF, sparse coding and image patches. With sparse coding as an intermediate layer, CRF is learned in a feature-adaptive manner; meanwhile with CRF as the output layer, the dictionary is learned under structured supervision. For efficient and effective joint learning, we develop a max-margin approach via a stochastic gradient descent algorithm. Experimental results on the Graz-02 and PASCAL VOC datasets show that our model performs favorably against state-of-the-art top-down saliency methods for target object localization. In addition, the dictionary update significantly improves the performance of our model. We demonstrate the merits of the proposed top-down saliency model by applying it to prioritizing object proposals for detection and predicting human fixations.
URI: http://localhost/handle/Hannan/185675
volume: 39
issue: 3
More Information: 576,
588
Appears in Collections:2017

Files in This Item:
File SizeFormat 
7442536.pdf1.75 MBAdobe PDF
Title: Top-Down Visual Saliency via Joint CRF and Dictionary Learning
Authors: Jimei Yang;Ming-Hsuan Yang
Year: 2017
Publisher: IEEE
Abstract: Top-down visual saliency is an important module of visual attention. In this work, we propose a novel top-down saliency model that jointly learns a Conditional Random Field (CRF) and a visual dictionary. The proposed model incorporates a layered structure from top to bottom: CRF, sparse coding and image patches. With sparse coding as an intermediate layer, CRF is learned in a feature-adaptive manner; meanwhile with CRF as the output layer, the dictionary is learned under structured supervision. For efficient and effective joint learning, we develop a max-margin approach via a stochastic gradient descent algorithm. Experimental results on the Graz-02 and PASCAL VOC datasets show that our model performs favorably against state-of-the-art top-down saliency methods for target object localization. In addition, the dictionary update significantly improves the performance of our model. We demonstrate the merits of the proposed top-down saliency model by applying it to prioritizing object proposals for detection and predicting human fixations.
URI: http://localhost/handle/Hannan/185675
volume: 39
issue: 3
More Information: 576,
588
Appears in Collections:2017

Files in This Item:
File SizeFormat 
7442536.pdf1.75 MBAdobe PDF
Title: Top-Down Visual Saliency via Joint CRF and Dictionary Learning
Authors: Jimei Yang;Ming-Hsuan Yang
Year: 2017
Publisher: IEEE
Abstract: Top-down visual saliency is an important module of visual attention. In this work, we propose a novel top-down saliency model that jointly learns a Conditional Random Field (CRF) and a visual dictionary. The proposed model incorporates a layered structure from top to bottom: CRF, sparse coding and image patches. With sparse coding as an intermediate layer, CRF is learned in a feature-adaptive manner; meanwhile with CRF as the output layer, the dictionary is learned under structured supervision. For efficient and effective joint learning, we develop a max-margin approach via a stochastic gradient descent algorithm. Experimental results on the Graz-02 and PASCAL VOC datasets show that our model performs favorably against state-of-the-art top-down saliency methods for target object localization. In addition, the dictionary update significantly improves the performance of our model. We demonstrate the merits of the proposed top-down saliency model by applying it to prioritizing object proposals for detection and predicting human fixations.
URI: http://localhost/handle/Hannan/185675
volume: 39
issue: 3
More Information: 576,
588
Appears in Collections:2017

Files in This Item:
File SizeFormat 
7442536.pdf1.75 MBAdobe PDF